{"id":"W4282826100","doi":"10.1101/2022.06.10.495595","title":"Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institute for Advanced Research; McKnight Foundation; Alfred P. Sloan Foundation; National Institutes of Health; National Science Foundation","keywords":"Computer science; Population; Decoding methods; Transfer of learning; Architecture; Artificial intelligence; Sight; Transformer; Biological neuron model; Theoretical computer science; Machine learning; Artificial neural network; Algorithm; Geography; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006466234,0.0004207535,0.0005316609,0.0005715022,0.0002458896,0.001009199,0.00104278,0.0006244786,0.002025962],"category_scores_gemma":[0.002640932,0.0003977134,0.0007509982,0.0005955753,0.001038041,0.003583463,0.001378552,0.001385955,0.0006245848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005592926,"about_ca_system_score_gemma":0.0006158101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00336253,"about_ca_topic_score_gemma":0.004182542,"domain_scores_codex":[0.9998254,0.0000545619,0.0000102678,0.0000526595,0.00003428407,0.0000228504],"domain_scores_gemma":[0.9993381,0.0003046299,0.00006827167,0.0001741519,0.00005748591,0.00005728479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001699847,0.00005853733,0.002081275,0.0001127563,0.00008287925,0.0001671873,0.0004051375,0.6358624,0.01728224,0.1802373,0.002549351,0.160991],"study_design_scores_gemma":[0.000004012435,0.0000145081,0.0000958249,0.000004679635,0.00000487528,0.00002412678,0.00001423138,0.9341804,0.0009758436,0.06414654,0.0005288667,0.000006144206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01841818,0.00007278968,0.9800521,0.0001522985,0.000011995,0.00001030509,0.00007220332,0.0003823408,0.0008278725],"genre_scores_gemma":[0.7471778,0.0004340177,0.2477921,0.0001843243,0.00003686015,0.00008189473,0.0003618934,0.0003071977,0.003623885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00336253,"threshold_uncertainty_score":0.006777525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01528194294722204,"score_gpt":0.2260996494274213,"score_spread":0.2108177064801993,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}